克劳德工作流
经 AI Skill Hub 精选评估，克劳德工作流 获评「强烈推荐」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 8.0 分，适合有一定技术背景的用户使用。
📚 深度解析
克劳德工作流 工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。
在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 8.0 分，是同类 Agent 工作流中的精选推荐。
📋 工具概览
克劳德工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
📖 中文文档
克劳德工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
# 克隆仓库 git clone https://github.com/byerlikaya/claude-starter-kit cd claude-starter-kit # 查看安装说明 cat README.md # 按 README 完成环境依赖安装后即可使用
- 访问 GitHub 仓库获取工作流文件
- 在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
- 上传工作流文件
- 按照提示配置必要的环境变量和 API Key
- 运行测试确认流程正常后投入使用
# 查看帮助 claude-starter-kit --help # 基本运行 claude-starter-kit [options] <input> # 详细使用说明请查阅文档 # https://github.com/byerlikaya/claude-starter-kit
# claude-starter-kit 配置说明 # 查看配置选项 claude-starter-kit --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量（覆盖配置文件） export CLAUDE_STARTER_KIT_CONFIG="/path/to/config.yml"
简介
<img src="assets/logo.svg" alt="Claude Starter Kit" width="460">
Not one assistant. An engineering team that actually runs.
12 specialist agents plan the work, build it, put it through security and test review, then close it
🇬🇧 English · 🇹🇷 Türkçe
<img src="assets/studio-flow.gif" alt="A delegation assembling itself in the panel: agents appear as they spawn, dashes travel from the session down each live branch, a workflow run fills with its members, and one agent fails" width="880">
<sub>Twelve agents on one canvas as they spawn — kit agents in their own colours, Claude's built-ins in theirs.<br>The panel is in this repository; see <a href="#seeing-it-run">Seeing it run</a>.</sub>
</div>
---
What's inside
Every agent, every skill, and the real
applies relationships — grouped by stage, each agent its own hue; the centre is the main thread that orchestrates them.
| Component | Count | What it is |
|---|---|---|
| **Agents** | 12 | Thin triggers — *who* owns a domain and *when* they fire |
| **Skills** | 40 | The method, written once, applied by whoever needs it |
| **Slash commands** | 11 | /brainstorm-csk · /plan-csk · /review-csk · /ship-csk · /handoff-csk · /update-csk · /doctor-csk · /board-csk · /gates-csk · /skill-csk · /studio-csk |
| **Hooks** | 12 | The gates, plus session measurement and routing |
| **Discipline** | 1 | Principles, workflow, Definition of Done, prohibitions — imported by your CLAUDE.md |
<details> <summary>🪝 <b>All 12 hooks — which gate holds what</b></summary>
| Hook | Role |
|---|---|
route-hint.sh | Names the owning agent alongside every prompt, so specialists run without you asking |
guard-bash.sh | Tool-level command gate: commit/push approval, destructive ops, remote-code-exec, hook tampering |
guard-write.sh | The same protection on the Write/Edit side — a gate you can silently delete is not a gate. It normalises the target path before matching it, so a gate file cannot be reached under a different spelling. |
guard-commit-scan.sh | Runs the real trace and secret scanners from PreToolUse, so the commit gate works where core.hooksPath cannot be set |
context-usage.sh | Reads the real token count from the transcript and injects it every turn |
session-guard.sh | Warns once at 75% context fill and once at 90% — never blocks a turn |
session-rehydrate.sh | Re-surfaces the handover after /compact or /clear |
skill-trust.sh | Names any skill or agent Claude Starter Kit never shipped and you never accepted |
session-stats.sh | Reports what the session actually did — failing tool loops, repeated prompts, interrupts. reflect and handoff read it, so a retrospective rests on the record rather than on recollection |
session-update-check.sh | Says once, when a session opens, that a newer kit version is published — each edition compared against the channel that will deliver it. The lookup runs detached and at most daily, so an offline or proxied machine costs the session opening nothing; CSK_NO_UPDATE_CHECK=1 turns it off |
board.sh | The team board engine: claims a work item, hands it over, completes it. Off unless a repo runs /board-csk init |
board-sync.sh | Puts a team's board state into a session. Reads a local cache at session start and refreshes it detached, so an unreachable remote costs the session opening nothing; CSK_NO_BOARD=1 turns it off |
Two git hooks — pre-commit and commit-msg — run the trace, secret, repo-bloat and private-path scans. The last one exists because a path that only lives on your machine reaches a shared repo by being pasted, not by being typed: it blocks your own $HOME automatically, and the internal project, client and host names only you can recognise come from a gitignored .private-terms.txt (.private-allowlist.txt is the escape). The plugin edition ships all of these except skill-trust.sh, which decides what is kit-owned from the kit-manifest.txt an installer writes and the plugin never creates.
</details>
<details> <summary>📚 <b>All 40 skills — the full catalogue, generated from each skill</b></summary>
| Skill | What it does |
|---|---|
a11y | Frontend accessibility audit (WCAG): semantic HTML, keyboard access, focus management, contrast, ARIA, screen readers. |
adr | Architecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. |
api-design | API contract design: resource naming, error model, versioning, pagination, backward compatibility, OpenAPI. |
automode-policy | Auto-mode classifier config: inspect what the classifier that now answers permission prompts is configured with, and catch the silent… |
brainstorm | Divergent discovery BEFORE planning: turn a fuzzy ask into 2–4 scoped options + named unknowns, pick a direction, hand to spec-planning. |
ci-pipeline | CI pipeline discipline: lint→build→test→quality→security, fail-fast, deterministic build, secret handling, PR gates. |
code-review-csk | Code review discipline: severity-ranked, reasoned feedback on whether a change improves the system's overall code health. |
commit-message | Conventional Commits: reads the staged diff and proposes type(scope): summary, with body/footer when needed. |
confidence-check | Readiness gate BEFORE writing implementation code: does this already exist, does it fit the project's architecture, is the API claim… |
db-migration | Apply schema migrations safely: detect the tool, classify the change by risk, gate destructive ones behind approval, back up in prod,… |
dependency-audit | Dependency risk assessment, read-only: known CVEs, deprecated packages, licence compliance, maintenance status, lockfile integrity, and a… |
dependency-upgrade | Bring dependencies current without breaking the build: find what is vulnerable, deprecated or behind, classify each target version by… |
deploy | Ship a build reversibly — to a host you manage or a platform that manages it. |
devarch-module | DevArchitecture backend pattern: MediatR CQRS handler/command/query, IResult/IDataResult, Autofac AOP chain, FluentValidation, i18n. |
docs-writer | Keeps documentation in sync with the code: README, usage and related docs when a public API or behavior changes. |
eval-grader | Measure output quality, don't vibe it: score a generative task with a two-layer grader — deterministic code metrics + per-dimension… |
frontend-design | Visual and UX design quality for interfaces: hierarchy, spacing rhythm, typographic scale, a restrained color system, layout composition,… |
frontend-rn-expo | OPTIONAL, stack-specific: React Native + Expo (prebuild). |
frontend | Stack-agnostic frontend discipline (web · mobile · desktop): component structure, state, data fetching, loading/empty/error states,… |
handoff | Session handover: when context fills, a phase closes, or the topic changes, write an action-oriented handover to docs/SESSION_STATE.md,… |
i18n-integrity | Translation integrity: every key present in every language, no hardcoded strings, consistent placeholders and plurals. |
incident-runbook | Production incident response: diagnose → mitigate → resolve, then a blameless postmortem and a repeatable runbook. |
iterate | Refine-to-Done loop: repeat until tests green + review clean + nothing deferred; bounded. |
mcp-builder | Build a Model Context Protocol (MCP) server so an AI client can call your tools/resources: design tool schemas, pick a transport, handle… |
observability | Stack-agnostic observability: structured logs, correlation ids, metrics and traces; no PII or secrets in logs. |
performance | Stack-agnostic performance: measure first, find the bottleneck, then optimise. |
privacy-compliance | KVKK/GDPR audit method: data inventory, purpose/basis/retention, minimisation, consent, transparency, data-subject rights, cross-border… |
red-team | Attacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted content; verifies… |
reflect | Retrospective self-audit after nontrivial work: unverified assumptions, skipped items, is-this-the-right- approach — findings, not code. |
release | Versioning and CHANGELOG: SemVer mapped from Conventional Commits, Keep a Changelog format, tagging, pre-release gates. |
security-scan | Stack-agnostic security audit: map the attack surface, trace untrusted input to dangerous calls, surface dependency and configuration flaws. |
sonarqube-check | SonarQube quality gate, any language, no company server needed: run SonarQube Community Build locally (Docker), read the real gate +… |
spec-planning | Spec-first planning: task breakdown, measurable acceptance criteria, dependency order, risk priority. |
systematic-debugging | Root-cause a bug before touching a fix: reproduce, isolate, form and test a hypothesis, confirm the cause, then fix and verify. |
teamboard | Shared team board: claim a work item before starting, hand it over, finish it. |
testing | The how of testing: pyramid, AAA, isolation, risk coverage, determinism. |
threat-model | Scope a security audit BEFORE scanning, to cut false positives: map assets, entry points, trust boundaries and 5-8 domain-specific attack… |
token-budget | Context/token discipline: subagent isolation, output = summary, move-to-file, delegation threshold, lean skills. |
trace-scan | Trace scan (§4.1/§4.2): before a commit, scans the staged changes and the message for AI traces (co-author trailers, footers, robot… |
worktree | Isolate risky or parallel file-mutating work in a git worktree so the main tree's uncommitted changes are never clobbered. |
</details>
---
Install
Two entry points: start.sh for a new project, adopt.sh for one already in motion. Every channel runs the same two commands.
```bash
npx — nothing to install
npx @byerlikaya/claude-starter-kit # new project npx @byerlikaya/claude-starter-kit adopt # existing project npx @byerlikaya/claude-starter-kit@latest update # refresh an installed kit
Quick start
npx @byerlikaya/claude-starter-kit # new project — setup wizard
npx @byerlikaya/claude-starter-kit adopt # existing project — handover on a branchThen open Claude Code and run /doctor-csk: it confirms the install is wired and scores the project's readiness. Homebrew, a release tarball and a plugin edition are in Install.
Release tarball — no package manager
gh release download --repo byerlikaya/claude-starter-kit -p '.tgz' && tar xzf claude-starter-kit-.tgz bash start.sh # new project bash adopt.sh # existing project (re-run it to update)
**Windows:** Claude Starter Kit is bash-based. Run it in **Git Bash** ([git-scm.com](https://git-scm.com)); WSL works as a fallback. The gate hooks are shell scripts, so **Git Bash (or WSL) is what makes them run** — on a Windows machine with neither, Claude Code enables its PowerShell tool automatically and the hooks cannot execute, which means no gates. That configuration is not supported by the gate layer, and the installers cannot run there either. With Git Bash present the gates cover **both** shells: the PowerShell tool is on by default for claude.ai and Console accounts, and its commands go through the same rules (`Remove-Item -Recurse -Force`, `… | iex`, `Get-Content .env`, and the rest).
**Plugin edition** — just the agents, skills and gate hooks inside your existing Claude Code, no scaffolding:
An installed plugin stays on the version you installed until you ask for a newer one, so run claude plugin marketplace update byerlikaya then claude plugin update claude-starter-kit, and restart to apply.
高质量的开源AI工作流项目
- 构建多智能体协作系统的 Agent 开发者
- 跨境业务、多语言内容运营团队
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
⚡ 核心功能
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 构建多智能体协作系统的 Agent 开发者
- 跨境业务、多语言内容运营团队
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
👥 适合人群
🎯 使用场景
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
⚖️ 优点与不足
- +MIT 协议，可免费商用
- +大幅减少重复性人工操作
- +可视化流程，清晰直观
- +可扩展性强，支持复杂场景
- −初始配置和调试需投入一定时间
- −强依赖外部服务的稳定性
- −复杂场景需具备一定技术基础
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。
🔗 相关工具推荐
❓ 常见问题 FAQ
AI Skill Hub 点评：克劳德工作流 的核心功能完整，质量优秀。对于自动化工程师和运维人员来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。
| 原始名称 | claude-starter-kit |
| 原始描述 | 开源AI工作流：A disciplined engineering team for Claude Code — not a prompt. 11 specialist age。⭐9 · Shell |
| Topics | ai-agentsautomationshell |
| GitHub | https://github.com/byerlikaya/claude-starter-kit |
| License | MIT |
| 语言 | Shell |
收录时间：2026-07-12 · 更新时间：2026-07-12 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
🤖 交给 Agent 安装 · 克劳德工作流
选择 Agent 类型，复制安装指令后粘贴到对应客户端